co-marketing
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely descriptive and provides strategic frameworks for co-marketing. It contains no executable scripts, shell commands, or automated integrations.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions include steps to read project-specific context from files like
.agents/product-marketing.md. While this represents an ingestion point for external data, the skill lacks any 'dangerous' capabilities (such as network access, file writing, or command execution) that could be leveraged for exploitation. - [EXTERNAL_DOWNLOADS]: References to external tools like Crossbeam, Introw, and PartnerStack are documented via internal links to local guides (e.g.,
../../tools/integrations/crossbeam.md) and do not perform active network requests or package installations. - [DATA_EXFILTRATION]: There are no patterns suggesting data exfiltration. The skill processes user-provided marketing information locally within the agent's context.
Audit Metadata